We invite submissions to the First Workshop on Human–Scene Interaction (HSI) at ECCV 2026. This workshop focuses on modelling and generating human motion and behaviour grounded in the surrounding scene. The goal is to bring together research from computer vision, graphics, robotics, and multimodal learning to advance scene-aware embodied agents.
We welcome both archival and non-archival submissions.
Topics of Interest
Topics include, but are not limited to:
Scene-conditioned human motion generation
Human–scene and human–object interaction modelling
Referring expression understanding and grounding in 3D scenes
Language understanding and grounded communication for embodied agents
Vision–language–motion alignment and grounding
Vision-language-action (VLA) models for embodied agents
Multimodal learning for motion and interaction
Datasets, benchmarks, and evaluation for interaction
Affordance learning and scene understanding
Physically-based simulation of interaction
Applications in robotics, animation, AR/VR, and embodied communication
Technical report accompanying the challenge submissions.
Must present original, unpublished work.
Will undergo peer review.
Accepted papers will be published in the ECCV 2026 Workshop Proceedings (Springer LNCS).
Papers must follow the ECCV formatting guidelines.
May include previously published work, work under review, or ongoing research.
Intended for presentation only (poster or oral), and will not be included in the proceedings.
Ideal for sharing recent results, demos, or position papers and fostering discussion within the community.
Submission links: To be announced
Important Dates
Submission deadline: July 7, 2026
Notification: July 31, 2026
Workshop: September 2026
The workshop will also host a challenge on scene-aware gesture generation based on the MM-Conv dataset. Participation in the challenge requires a paper submission describing the method. All challenge submissions will be considered archival submissions and will undergo peer review. Please refer to the following for details:
Dataset: More information will be announced soon.
Challenge details: More information will be announced soon.